1 files changed, 182 insertions, 7 deletions

diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index cc5a2545dd41..2b46eb41643b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -12,6 +12,8 @@
 #include <asm/proto.h>
 #include <asm/reboot_fixups.h>
 #include <asm/reboot.h>
+#include <asm/pci_x86.h>
+#include <asm/virtext.h>
 
 #ifdef CONFIG_X86_32
 # include <linux/dmi.h>
@@ -21,6 +23,8 @@
 # include <asm/iommu.h>
 #endif
 
+#include <mach_ipi.h>
+
 /*
  * Power off function, if any
  */
@@ -36,7 +40,16 @@ int reboot_force;
 static int reboot_cpu = -1;
 #endif
 
-/* reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old]
+/* This is set if we need to go through the 'emergency' path.
+ * When machine_emergency_restart() is called, we may be on
+ * an inconsistent state and won't be able to do a clean cleanup
+ */
+static int reboot_emergency;
+
+/* This is set by the PCI code if either type 1 or type 2 PCI is detected */
+bool port_cf9_safe = false;
+
+/* reboot=b[ios] | s[mp] | t[riple] | k[bd] | e[fi] [, [w]arm | [c]old] | p[ci]
    warm   Don't set the cold reboot flag
    cold   Set the cold reboot flag
    bios   Reboot by jumping through the BIOS (only for X86_32)
@@ -45,6 +58,7 @@ static int reboot_cpu = -1;
    kbd    Use the keyboard controller. cold reset (default)
    acpi   Use the RESET_REG in the FADT
    efi    Use efi reset_system runtime service
+   pci    Use the so-called "PCI reset register", CF9
    force  Avoid anything that could hang.
  */
 static int __init reboot_setup(char *str)
@@ -79,6 +93,7 @@ static int __init reboot_setup(char *str)
                 case 'k':
                 case 't':
                 case 'e':
+                case 'p':
                         reboot_type = *str;
                         break;
 
@@ -360,6 +375,48 @@ static inline void kb_wait(void)
         }
 }
 
+static void vmxoff_nmi(int cpu, struct die_args *args)
+{
+        cpu_emergency_vmxoff();
+}
+
+/* Use NMIs as IPIs to tell all CPUs to disable virtualization
+ */
+static void emergency_vmx_disable_all(void)
+{
+        /* Just make sure we won't change CPUs while doing this */
+        local_irq_disable();
+
+        /* We need to disable VMX on all CPUs before rebooting, otherwise
+         * we risk hanging up the machine, because the CPU ignore INIT
+         * signals when VMX is enabled.
+         *
+         * We can't take any locks and we may be on an inconsistent
+         * state, so we use NMIs as IPIs to tell the other CPUs to disable
+         * VMX and halt.
+         *
+         * For safety, we will avoid running the nmi_shootdown_cpus()
+         * stuff unnecessarily, but we don't have a way to check
+         * if other CPUs have VMX enabled. So we will call it only if the
+         * CPU we are running on has VMX enabled.
+         *
+         * We will miss cases where VMX is not enabled on all CPUs. This
+         * shouldn't do much harm because KVM always enable VMX on all
+         * CPUs anyway. But we can miss it on the small window where KVM
+         * is still enabling VMX.
+         */
+        if (cpu_has_vmx() && cpu_vmx_enabled()) {
+                /* Disable VMX on this CPU.
+                 */
+                cpu_vmxoff();
+
+                /* Halt and disable VMX on the other CPUs */
+                nmi_shootdown_cpus(vmxoff_nmi);
+
+        }
+}
+
+
 void __attribute__((weak)) mach_reboot_fixups(void)
 {
 }
@@ -368,6 +425,9 @@ static void native_machine_emergency_restart(void)
 {
         int i;
 
+        if (reboot_emergency)
+                emergency_vmx_disable_all();
+
         /* Tell the BIOS if we want cold or warm reboot */
         *((unsigned short *)__va(0x472)) = reboot_mode;
 
@@ -404,12 +464,27 @@ static void native_machine_emergency_restart(void)
                         reboot_type = BOOT_KBD;
                         break;
 
-
                 case BOOT_EFI:
                         if (efi_enabled)
-                                efi.reset_system(reboot_mode ? EFI_RESET_WARM : EFI_RESET_COLD,
+                                efi.reset_system(reboot_mode ?
+                                                 EFI_RESET_WARM :
+                                                 EFI_RESET_COLD,
                                                  EFI_SUCCESS, 0, NULL);
+                        reboot_type = BOOT_KBD;
+                        break;
+
+                case BOOT_CF9:
+                        port_cf9_safe = true;
+                        /* fall through */
 
+                case BOOT_CF9_COND:
+                        if (port_cf9_safe) {
+                                u8 cf9 = inb(0xcf9) & ~6;
+                                outb(cf9|2, 0xcf9); /* Request hard reset */
+                                udelay(50);
+                                outb(cf9|6, 0xcf9); /* Actually do the reset */
+                                udelay(50);
+                        }
                         reboot_type = BOOT_KBD;
                         break;
                 }
@@ -426,7 +501,7 @@ void native_machine_shutdown(void)
 
 #ifdef CONFIG_X86_32
         /* See if there has been given a command line override */
-        if ((reboot_cpu != -1) && (reboot_cpu < NR_CPUS) &&
+        if ((reboot_cpu != -1) && (reboot_cpu < nr_cpu_ids) &&
                 cpu_online(reboot_cpu))
                 reboot_cpu_id = reboot_cpu;
 #endif
@@ -436,7 +511,7 @@ void native_machine_shutdown(void)
                 reboot_cpu_id = smp_processor_id();
 
         /* Make certain I only run on the appropriate processor */
-        set_cpus_allowed_ptr(current, &cpumask_of_cpu(reboot_cpu_id));
+        set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id));
 
         /* O.K Now that I'm on the appropriate processor,
          * stop all of the others.
@@ -459,17 +534,28 @@ void native_machine_shutdown(void)
 #endif
 }
 
+static void __machine_emergency_restart(int emergency)
+{
+        reboot_emergency = emergency;
+        machine_ops.emergency_restart();
+}
+
 static void native_machine_restart(char *__unused)
 {
         printk("machine restart\n");
 
         if (!reboot_force)
                 machine_shutdown();
-        machine_emergency_restart();
+        __machine_emergency_restart(0);
 }
 
 static void native_machine_halt(void)
 {
+        /* stop other cpus and apics */
+        machine_shutdown();
+
+        /* stop this cpu */
+        stop_this_cpu(NULL);
 }
 
 static void native_machine_power_off(void)
@@ -504,7 +590,7 @@ void machine_shutdown(void)
 
 void machine_emergency_restart(void)
 {
-        machine_ops.emergency_restart();
+        __machine_emergency_restart(1);
 }
 
 void machine_restart(char *cmd)
@@ -523,3 +609,92 @@ void machine_crash_shutdown(struct pt_regs *regs)
         machine_ops.crash_shutdown(regs);
 }
 #endif
+
+
+#if defined(CONFIG_SMP)
+
+/* This keeps a track of which one is crashing cpu. */
+static int crashing_cpu;
+static nmi_shootdown_cb shootdown_callback;
+
+static atomic_t waiting_for_crash_ipi;
+
+static int crash_nmi_callback(struct notifier_block *self,
+                        unsigned long val, void *data)
+{
+        int cpu;
+
+        if (val != DIE_NMI_IPI)
+                return NOTIFY_OK;
+
+        cpu = raw_smp_processor_id();
+
+        /* Don't do anything if this handler is invoked on crashing cpu.
+         * Otherwise, system will completely hang. Crashing cpu can get
+         * an NMI if system was initially booted with nmi_watchdog parameter.
+         */
+        if (cpu == crashing_cpu)
+                return NOTIFY_STOP;
+        local_irq_disable();
+
+        shootdown_callback(cpu, (struct die_args *)data);
+
+        atomic_dec(&waiting_for_crash_ipi);
+        /* Assume hlt works */
+        halt();
+        for (;;)
+                cpu_relax();
+
+        return 1;
+}
+
+static void smp_send_nmi_allbutself(void)
+{
+        send_IPI_allbutself(NMI_VECTOR);
+}
+
+static struct notifier_block crash_nmi_nb = {
+        .notifier_call = crash_nmi_callback,
+};
+
+/* Halt all other CPUs, calling the specified function on each of them
+ *
+ * This function can be used to halt all other CPUs on crash
+ * or emergency reboot time. The function passed as parameter
+ * will be called inside a NMI handler on all CPUs.
+ */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+        unsigned long msecs;
+        local_irq_disable();
+
+        /* Make a note of crashing cpu. Will be used in NMI callback.*/
+        crashing_cpu = safe_smp_processor_id();
+
+        shootdown_callback = callback;
+
+        atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
+        /* Would it be better to replace the trap vector here? */
+        if (register_die_notifier(&crash_nmi_nb))
+                return;         /* return what? */
+        /* Ensure the new callback function is set before sending
+         * out the NMI
+         */
+        wmb();
+
+        smp_send_nmi_allbutself();
+
+        msecs = 1000; /* Wait at most a second for the other cpus to stop */
+        while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
+                mdelay(1);
+                msecs--;
+        }
+
+        /* Leave the nmi callback set */
+}
+#else /* !CONFIG_SMP */
+void nmi_shootdown_cpus(nmi_shootdown_cb callback)
+{
+        /* No other CPUs to shoot down */
+}
+#endif